Artificial Intelligence and Machine Learning in the Diagnosis and Management of Stroke: A Narrative Review of United States Food and Drug Administration-Approved Technologies.

Stroke is an emergency in which delays in treatment can lead to significant loss of neurological function and be fatal. Technologies that increase the speed and accuracy of stroke diagnosis or assist in post-stroke rehabilitation can improve patient outcomes. No resource exists that comprehensively assesses artificial intelligence/machine learning (AI/ML)-enabled technologies indicated for the management of ischemic and hemorrhagic stroke. We queried a United States Food and Drug Administration (FDA) database, along with PubMed and private company websites, to identify the recent literature assessing the clinical performance of FDA-approved AI/ML-enabled technologies. The FDA has approved 22 AI/ML-enabled technologies that triage brain imaging for more immediate diagnosis or promote post-stroke neurological/functional recovery. Technologies that assist with diagnosis predominantly use convolutional neural networks to identify abnormal brain images (e.g., CT perfusion). These technologies perform comparably to neuroradiologists, improve clinical workflows (e.g., time from scan acquisition to reading), and improve patient outcomes (e.g., days spent in the neurological ICU). Two devices are indicated for post-stroke rehabilitation by leveraging neuromodulation techniques. Multiple FDA-approved technologies exist that can help clinicians better diagnose and manage stroke. This review summarizes the most up-to-date literature regarding the functionality, performance, and utility of these technologies so clinicians can make informed decisions when using them in practice.

Expediting Treatment of Trauma Patients in the Emergency Department: Rapid Trauma Evaluation (RTE).

BACKGROUND: Criteria for trauma determination evolves. We developed/evaluated a Rapid Trauma Evaluation (RTE) process for a trauma patient subset not meeting preestablished trauma criteria. METHODS: Retrospective study (July 2019 - May 2020) for patients either > 65 years with ground level fall within 24 hours or in a motorcycle collision (MCC) arriving by EMS not meeting ACS trauma-criteria. RTE process was immediate evaluation by nurse/EMT, room placement, physician notification, undressing/gowning, vital signs, head-to-toe assessment, upgrade trauma status. Number/type of admissions, discharges, trauma upgrades, LOS obtained via trauma-registry and chart-review. For comparison, historic controls (HC) were used [all patients meeting RTE criteria seen in the ED prior to RTE (Apr- June 2019)]. RESULTS: The RTE cohort (n=755) was 77% falls,23% MCCs, median age 82 [IQR 74-88] years; 42% male-Among falls, 3.2% required a modified-upgrade; 0.7% full-upgrade, 55% admitted [29.4% trauma). HC (n=575) was 92.3% falls, 7.7% MCCs, median age 81 (IQR: 67-88) years, 40.5% males-57.4% admitted (22% trauma). RTE MCC median age 42 (IQR:30-49) years, 84.4% male- 21.9% were upgraded [(6 modified-trauma; 1 full-trauma; 43.8% admitted (85.7% trauma)]. HC MCC median age 29 (IQR: 23-41) years, 95.5% male, 54.5% admitted (75% trauma]. No difference on demographics, admissions or discharges between groups (P>0.05) except HC MCC was younger (P<0.005). RTE median LOS was shorter than HC [203 (IQR: 147-278) minutes vs. 286 (IQR: 205-392) minutes, P<0.001]. CONCLUSIONS: Patients > 65 years with a ground level fall or in a MCC arriving via EMS not meeting ACS trauma criteria may benefit from RTE.